{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UHVLSUVJTHL6XG43MKCD5LHE7C","short_pith_number":"pith:UHVLSUVJ","schema_version":"1.0","canonical_sha256":"a1eab952a999d7eb9b9b62843eace4f8a9024d62218c394b3d2712c2e756d2c5","source":{"kind":"arxiv","id":"2603.25476","version":2},"attestation_state":"computed","paper":{"title":"How Class Ontology and Data Scale Affect Audio Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Gebhard, Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Manuel Milling, Simon Rampp","submitted_at":"2026-03-26T14:18:29Z","abstract_excerpt":"Transfer learning is a crucial concept within deep learning that allows artificial neural networks to benefit from a large pre-training data basis when confronted with a task of limited data. Despite its ubiquitous use and clear benefits, there are still many open questions regarding the inner workings of transfer learning and, in particular, regarding the understanding of when and how well it works. To that extent, we perform a rigorous study focusing on audio-to-audio transfer learning, in which we pre-train various model states on (ontology-based) subsets of AudioSet and fine-tune them on t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.25476","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T14:18:29Z","cross_cats_sorted":[],"title_canon_sha256":"b4a420aae04f853334ba68a11cb410d44a35e96e65832af71b7dce1288efc585","abstract_canon_sha256":"b9f50ac9a809c81d711a044f008283f5609090720815868c868e5af95d4cdc8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:43.879810Z","signature_b64":"HbAb3vBFEpDXI5W81OVBe9nScFpO/dGU5j61hiLusn8ddYyguNexRzWlWVWTkm1AamopjAsx+ZSWo9XucTzGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1eab952a999d7eb9b9b62843eace4f8a9024d62218c394b3d2712c2e756d2c5","last_reissued_at":"2026-05-20T00:05:43.879162Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:43.879162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Class Ontology and Data Scale Affect Audio Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Gebhard, Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Manuel Milling, Simon Rampp","submitted_at":"2026-03-26T14:18:29Z","abstract_excerpt":"Transfer learning is a crucial concept within deep learning that allows artificial neural networks to benefit from a large pre-training data basis when confronted with a task of limited data. Despite its ubiquitous use and clear benefits, there are still many open questions regarding the inner workings of transfer learning and, in particular, regarding the understanding of when and how well it works. To that extent, we perform a rigorous study focusing on audio-to-audio transfer learning, in which we pre-train various model states on (ontology-based) subsets of AudioSet and fine-tune them on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25476","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.25476/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.25476","created_at":"2026-05-20T00:05:43.879265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25476v2","created_at":"2026-05-20T00:05:43.879265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25476","created_at":"2026-05-20T00:05:43.879265+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHVLSUVJTHL6","created_at":"2026-05-20T00:05:43.879265+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHVLSUVJTHL6XG43","created_at":"2026-05-20T00:05:43.879265+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHVLSUVJ","created_at":"2026-05-20T00:05:43.879265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C","json":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C.json","graph_json":"https://pith.science/api/pith-number/UHVLSUVJTHL6XG43MKCD5LHE7C/graph.json","events_json":"https://pith.science/api/pith-number/UHVLSUVJTHL6XG43MKCD5LHE7C/events.json","paper":"https://pith.science/paper/UHVLSUVJ"},"agent_actions":{"view_html":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C","download_json":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C.json","view_paper":"https://pith.science/paper/UHVLSUVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25476&json=true","fetch_graph":"https://pith.science/api/pith-number/UHVLSUVJTHL6XG43MKCD5LHE7C/graph.json","fetch_events":"https://pith.science/api/pith-number/UHVLSUVJTHL6XG43MKCD5LHE7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C/action/storage_attestation","attest_author":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C/action/author_attestation","sign_citation":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C/action/citation_signature","submit_replication":"https://pith.science/pith/UHVLSUVJTHL6XG43MKCD5LHE7C/action/replication_record"}},"created_at":"2026-05-20T00:05:43.879265+00:00","updated_at":"2026-05-20T00:05:43.879265+00:00"}